Sorry for the updating delay on my end. As Rachelle mentioned in earlier blog posts, I also attended the ISPASS Conference towards the end of March. I listened to a couple presentations on GPU’s, CloudSuite, a talk that included information on Google’s MapReduce, and more. It was a very interesting experience to listen to Ph.D. level discussions in Computer Science. During the talk on CloudSuite, a suite of applications for evaluating server designs, it was interesting to hear the professionals in the room questioning the speaker about the applications in the suite. I believe I agree with the professionals in their disappointment that this suite does not take I/O into real consideration in its evaluation of the server, especially if this is to be marketed as a tool to use in a data center. Otherwise, I would consider using this suite to gather more data center application data for our research. It was also an awesome experience to meet some of the people that Rachelle and I met at ISPASS, including Duke!
In between CCSC South West Region Conference and ISPASS, I did perform classification calculations on the data we collected from SpecJBB, and last week I finished a program for parsing our data files into more manageable files. Yay! That has saved us a ton of time and headaches! So far we’ve seen that one run of SpecJBB is not being classified with the rest on a fairly regular basis. Granted, we’re not finished creating our data tables based on the results. However, a classification rate of 5 out 6 runs of SpecJBB being classified correctly is pretty cool. We’ll have to delve deeper into that run of SpecJBB and see what’s going on with it.
Also, we’ve gotten new power meters to use for collecting data!!!
So Jolie and I have data collected (again) with SpecJBB as part of our trace set. We ran all of our traces through our classification algorithm and now our task is getting our data into LaTex tables and then analyzing them. It’s not terribly exciting, but hopefully we’ll get finished sooner than we did last semester, since Jolie made a parsing script that gets the relevant data we want to look at. It’s also easier because we can just copy-paste the data into the tables I made last semester. So yay! The faster we get this analyzing and data collecting done there’s more of a chance for us to actually write a technical paper of our research for the past year.
Also, Dr. Rivoire and I are in the process of finishing up our Grace Hopper application. We turned in the actual poster submission, but now we’re doing the scholarship application so I can get funding to actually go to the conference. This pretty much involves a letter of recommendation (Rivoire’s court), a 500-word essay on why I want to go and what I’ll do with the experience (yay feminism!), and my resume. Pretty much the hardest part — my resume’s pretty dinky considering I’ve only had two real significant jobs in my lifetime, but at least those jobs were awesomesauce. Making a resume is so difficult though. No me gusta.
Anyway, just thought I’d update you all on the happenings around here, but that’s pretty much it (unless Jolie wants to talk about her conference experience, maybe?). Toodles!
So sorry for not updating the blog regularly — it’s been a pretty crazy semester what with all the school projects that Jolie and I have had to do, but hopefully I can get back on track now that I have three major projects left for each of my classes. I think Jolie has one; not sure. But never fear! Jolie and I haven’t been idle in our work; in fact, we have six fresh runs of SpecJBB (three on each of our machines) and data on those runs that we just have to analyze. So hopefully next week we’ll be able to post our results and findings.
Anyway, last week Jolie and I went to the International Symposium on Performance Analysis of Systems and Software (ISPASS) where we attended talks about applications and benchmarks, analytic and statistical models, online profiling, cache and memory systems, and GPUs. I attended the talks about GPUs, but as interesting as they were, a lot of the information went completely over my head. I can’t remember what Jolie went to, so I’ll let her create her own post about her experience.
The most interesting part of the trip were the people. We met people from different universities across the world, people who worked at Microsoft Research and Google, and people who worked for various corporations involved in research. We had dinner with the group that put ISPASS together and a few of them work at Duke University; they talked to Dr. Rivoire about possible funding for getting a master’s degree there. I didn’t think I’d ever want to go get my master’s so soon after getting my bachelor’s, but heck, why not? Sounds exciting.
Anyway, I’m having intense writer’s block, so I think I’ll stop here and let Jolie take over. Toodles!
This past weekend I attended the CCSC South West Region Conference at CSU Northridge. It was a great experience! The attendees made me feel very welcomed there! It was a small conference, and a majority of the papers and presentations were based on research in education aspects of Computer Science. The student poster session had 5 posters, including mine. I had lots of great questions and receptions to my presentation. I’m really glad that I had the opportunity to attend the conference! 🙂
Rachelle spent most of last week finishing her 2-page abstract paper and submitted it to the Grace Hopper Conference. It was quite the experience trying to discuss our work in the span of two pages.
Rachelle and I have been hard at work preparing for our conferences. Rachelle is finishing a short abstract to submit for the Grace Hopper Conference, and my poster abstract has been accepted into the CCSC South Western Region Conference. My travel arrangements have been booked, and my poster is just about to get printed.
As far as SPECJBB goes, we have collected our data from running the application on both LolCat and Rageface. Next we will be running the data through the Random Forest classification algorithm to see how our newly expanded data collection classifies together.
Jolie and I are still hacking away at our abstracts for our respective conferences that we’re going to (Jolie at Northridge, me at GHC). Jolie’s pretty much done with her two paragraph summary and I believe she’s started creating the basics of her poster. Rivoire and I are still going through my paragraph to tweak the wording and whatnot. I have an outline for my poster, but I still have to write the overall, 2 page abstract.
Since Jolie is graduating, she’ll be going to Northridge this semester. I’m not graduating until next fall, which is just as well, because the GHC conference isn’t until October, I think. It’s a little strange that GHC wants the abstracts submitted so early for a conference so late, but at least I’ll get everything done earlier rather than later.
Anyway, we’re in the process of completing our last run of SpecJBB (should be finished already, actually) on our first machine, Lolcat. We started installing Spec on Rageface at the same time so we could immediately switch meters and jump into collecting three runs again. Installing Spec is a bit of a hassle since we had to update the version of Java JDK and JRE we were using. Plus the installation itself takes a super long time, so we just left it alone while we worked on our abstracts.
Tomorrow we plan on running Spec on Rageface for real. We have to configure the scripts we use, but that should be somewhat easy since we already did so on Lolcat.
Well, that’s all for updates now. Toodles!
This week Rachelle and I have been attempting to get Spec JBB to run its full length on one of our machines. Thus far it has not liked running its full length when starting it via an ssh login to our data collecting machine, so we have resorted to traveling to where the monitor and keyboard attached to the machine is physically located and running the benchmark from there. We did overcome the hurdle of the Java Virtual Machine running out of memory – use the command line flag -Xmx#g (Insert an actual number for the # mark, but it can’t be larger than the amount of RAM on the machine. Preferably it should be lower, or you run the risk of the machine running out of much needed memory.).
Rachelle and I have also begun writing abstracts for submission to the conferences that each of us will be attending. Rachelle has to somehow condense a summary of her work into 100 words… We have also started work on our posters. A couple fellow research assistants were kind enough to share their poster with us so we can have an idea of what information to include on it.
That’s about all we have for now until we have finished collecting Spec JBB data.